https://github.com/JeanKossaifi/tensorly-notebooks

Tensor methods in Python with TensorLy
https://github.com/JeanKossaifi/tensorly-notebooks

deep-learning tensor-algebra tensor-methods tensorly

Last synced: 3 months ago
JSON representation

Tensor methods in Python with TensorLy

• Host: GitHub
• URL: https://github.com/JeanKossaifi/tensorly-notebooks
• Owner: JeanKossaifi
• Created: 2017-08-05T01:30:17.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2023-02-13T10:31:52.000Z (about 2 years ago)
• Last Synced: 2024-11-13T22:03:18.372Z (3 months ago)
• Topics: deep-learning, tensor-algebra, tensor-methods, tensorly
• Language: Jupyter Notebook
• Homepage:
• Size: 2.79 MB
• Stars: 429
• Watchers: 15
• Forks: 126
• Open Issues: 3
• Metadata Files:
  • Readme: README.rst

Awesome Lists containing this project

• Awesome-pytorch-list-CNVersion - tensorly-notebooks
• Awesome-pytorch-list - tensorly-notebooks

README

        
======================================

Tensor methods in Python with TensorLy

======================================

This repository contains a series of tutorials and examples on tensor learning, with implementations in Python using `TensorLy `_, and how to combine tensor methods and deep learning using the `MXNet `_,  `PyTorch `_ and `TensorFlow `__ frameworks as backends.

Installation

============

You will need to have the latest version of TensorLy installed to run these examples as explained in the `instructions `_.

The easiest way is to clone the repository::

   git clone https://github.com/tensorly/tensorly

   cd tensorly

   pip install -e .

Then simply clone this repository::

   git clone https://github.com/JeanKossaifi/tensorly_notebooks

You are ready to go!

Table of contents

=================

1 - Tensor basics

-----------------

- `Manipulating tensors (unfolding, n-mode product, etc) `_

2 - Tensor decomposition

------------------------

- `CP decomposition `_

- `Tucker decomposition `_

3 - Tensor regression

---------------------

- `Low-rank tensor regression `_

4 - Tensor methods and deep learning with the MXNet backend

-----------------------------------------------------------

- `Tucker decomposition via gradient descent `_

- `Tensor regression networks `_

5 - Tensor methods and deep learning with the PyTorch backend

-------------------------------------------------------------

- `Tucker decomposition via gradient descent `_

- `Tensor regression networks `_

6 - Tensor methods and deep learning with the TensorFlow backend

----------------------------------------------------------------

- `Tucker decomposition via gradient descent `__

Useful resources

=================

The following are very useful sources of information and I highly recomment you check them out:

- `TensorLy documentation `_ : extensive documentation, API, etc.

- `Deep Learning - The Straight Dope `_ : a great tutorial for Deep Learning using MXNet, by Zack Lipton.

- `Deep Learning with PyTorch `_ : another great tutorial, this time with PyTorch, by Soumith Chintala.

- The `fast.ai cource `__ : a great course that teaches Deep Learning from the start, and build up all the way to state-of-the-art models.